© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1821
    Prev
    Next
    INDEX
    Explanations

    academic/technical text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Decompiled
    -0.27
     spel
    -0.22
    écoute
    -0.22
    	templateUrl
    -0.22
    polator
    -0.20
     UClass
    -0.19
    лав
    -0.19
    çĿ
    -0.18
    rot
    -0.18
    ä½İä½į
    -0.18
    POSITIVE LOGITS
    ":[{↵
    0.21
    intage
    0.21
    缸åħ³è´Łè´£
    0.21
    çĽħ
    0.21
    )size
    0.20
    ķìĿ¸
    0.20
    .sendStatus
    0.20
    .getCurrentUser
    0.20
    åħļæĢ»
    0.20
    åĵī
    0.19
    Activations Density 0.001%

    No Known Activations